---
base_model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
datasets:
  - p1atdev/ja-stackoverflow
license: other
license_name: deepseek
license_link: https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL
model_creator: DeepSeek
model_name: Deepseek Coder 7B Instruct
model_type: deepseek
prompt_template: 'You are an AI programming assistant, utilizing the Deepseek Coder
  model, developed by Deepseek Company, and you only answer questions related to computer
  science. For politically sensitive questions, security and privacy issues, and other
  non-computer science questions, you will refuse to answer.
  ### Instruction:
  {prompt}
  ### Response:
  '
---

# Deepseek Coder 7B Instruct ja-stackoverflow SFT - GGUF

## Description

This repository contains models trained(QLoRA-SFT) based on the following models:
- Model creator: [DeepSeek](https://huggingface.co/deepseek-ai)
- Original model: [Deepseek Coder 7B Instruct v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5)
- Train Data: [日本語版 Stack Overflow](https://huggingface.co/datasets/p1atdev/ja-stackoverflow)
  - accepted_answer_score > 2 and popular_answer_score > 2